board_tile_create

SERVERBreakpoint SOURCEbreakpoint-mcp

Medium RISK CLASS

Category Write

Parameters 93 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/breakpoint-mcp/board-tile-create.md

WHAT IT DOES

What board_tile_create does on Breakpoint

AI agents use board_tile_create to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.

Parameter	Type	Required	Description
`cols`	integer	Yes	Grid column count (cell x ranges 0..cols-1)
`path`	string	Yes	Where to save the board scene, e.g. res://ui/board/TileBoard.tscn
`rows`	integer	Yes	Grid row count (cell y ranges 0..rows-1)
`paint`	object	—	Fill the whole grid with one tile (needs an existing `tileset` that has the source); omitted → cells stay empty (a coordinate frame only)
`confirm`	boolean	—	Auto-approve this destructive action (skip the confirmation prompt)
`tileset`	string	—	Existing TileSet res:// .tres to bind; omitted → a fresh empty TileSet is created at <scene>_tiles.tres to establish the tile size
`overwrite`	boolean	—	Overwrite an existing board at `path` (default false)
`tile_size`	array	—	Tile cell size [w, h] in px (default [64, 64]); the coordinate frame board_tile_place snaps to
`layer_name`	string	—	TileMapLayer node name (default "Cells")

Parameters from the server's own tool schema.

RISK

Why board_tile_create is rated Medium

While the description header mentions 'DESTRUCTIVE,' the actual tool behavior—creating and configuring scene objects, tilesets, and tilemaps, then saving—constitutes data creation and modification that can be undone (files can be deleted, scenes modified or reverted). This is Write, not Destructive.

From the tool's definition Tool description states it 'writes a scene' and 'Adds no addon method — decomposes onto scene.new → tileset.create → tilemaplayer.create → tilemap.set_cells_rect → scene.save.' The description itself explicitly ends with 'DESTRUCTIVE (writes a scene, an' but…

Risk signalsAccepts file system path (path) · High parameter count (11 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs board_tile_create safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For board_tile_create, this is the rule to start with:

board_tile_create Rate-limited

board_tile_create stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "board_tile_create": {
      "limits": [
        {
          "counter": "board_tile_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every board_tile_create call is checked against it from then on.

FAQ

Questions about board_tile_create

What does the board_tile_create tool do? +

Build a tile-backed board scene: a TileMapLayer grid whose cells are addressable by integer [x, y] tile coordinates (cols wide × rows tall). The layer binds a TileSet — a supplied tileset .tres, or a fresh empty one created at <scene>_tiles.tres — so it has a real tile_size (the coordinate frame placement uses); paint optionally fills the whole grid with one tile from the bound tileset. General-purpose — cells carry only coordinates. Adds no addon method — decomposes onto scene.new → tileset.create → tilemaplayer.create → tilemap.set_cells_rect → scene.save. DESTRUCTIVE (writes a scene, and a TileSet .tres unless tileset is supplied) — gated by confirmation. Returns the layer path + grid dimensions + tile size. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does board_tile_create accept? +

board_tile_create accepts 9 parameters: cols, path, rows, paint, confirm, tileset, overwrite, tile_size, layer_name. Required: cols, path, rows. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on board_tile_create? +

Register the Breakpoint MCP server in PolicyLayer and add a rule for board_tile_create: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Breakpoint. Nothing to install.

What risk level is board_tile_create? +

board_tile_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit board_tile_create? +

Yes. Add a rate_limit block to the board_tile_create rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block board_tile_create completely? +

Set action: deny in the PolicyLayer policy for board_tile_create. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides board_tile_create? +

board_tile_create is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Breakpoint, and thousands of servers like it.

This server

All 274 Breakpoint tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →